© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13029
    Prev
    Next
    INDEX
    Explanations

    capacitor and capacitance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     retten
    -1.32
    %,
    -1.31
     herstellen
    -1.30
     ingenuity
    -1.27
     ausgewählt
    -1.25
     pegatina
    -1.23
     allerlei
    -1.21
     schuld
    -1.21
    だったり
    -1.21
     schrift
    -1.21
    POSITIVE LOGITS
    ージ
    1.27
    uF
    1.27
    </h3>
    1.27
     ॥
    1.24
    cstdio
    1.24
     time
    1.17
     dựng
    1.17
     kõik
    1.16
     restricting
    1.16
    ماش
    1.15
    Activations Density 0.018%

    No Known Activations